Skip to content

Why is there no dino loss or clip loss during evaluation? #89

@SmolBoi96

Description

@SmolBoi96

I understand from #2 that these losses are intentionally not retrieved during evaluation as they do not exist in the dictionary. Is there a reason why dino and clip features are not inferred from the evaluation dataset and the respective losses computed?

I am wondering if I misunderstood something and there is some limitation that makes this impossible. I would like to look at the clip and dino losses to check if the features lifting converges.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions